Paper Group ANR 1175
HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion. A Cryptanalysis of Two Cancelable Biometric Schemes based on Index-of-Max Hashing. Clustering and Classification Networks. Known-plaintext attack and ciphertext-only attack for encrypted single-pixel imaging. Saliency-Guided Attention Network for Image-Sentence Matching. …
HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion
| Title | HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion |
| Authors | Prodromos Kolyvakis, Alexandros Kalousis, Dimitris Kiritsis |
| Abstract | Learning embeddings of entities and relations existing in knowledge bases allows the discovery of hidden patterns in data. In this work, we examine the geometrical space’s contribution to the task of knowledge base completion. We focus on the family of translational models, whose performance has been lagging, and propose a model, dubbed HyperKG, which exploits the hyperbolic space in order to better reflect the topological properties of knowledge bases. We investigate the type of regularities that our model can capture and we show that it is a prominent candidate for effectively representing a subset of Datalog rules. We empirically show, using a variety of link prediction datasets, that hyperbolic space allows to narrow down significantly the performance gap between translational and bilinear models. |
| Tasks | Knowledge Base Completion, Knowledge Graph Embeddings, Link Prediction |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.04895v2 |
| https://arxiv.org/pdf/1908.04895v2.pdf | |
| PWC | https://paperswithcode.com/paper/hyperkg-hyperbolic-knowledge-graph-embeddings |
| Repo | |
| Framework | |
A Cryptanalysis of Two Cancelable Biometric Schemes based on Index-of-Max Hashing
| Title | A Cryptanalysis of Two Cancelable Biometric Schemes based on Index-of-Max Hashing |
| Authors | Kevin Atighehchi, Loubna Ghammam, Koray Karabina, Patrick Lacharme |
| Abstract | Cancelable biometric schemes generate secure biometric templates by combining user specific tokens and biometric data. The main objective is to create irreversible, unlinkable, and revocable templates, with high accuracy in matching. In this paper, we cryptanalyze two recent cancelable biometric schemes based on a particular locality sensitive hashing function, index-of-max (IoM): Gaussian Random Projection-IoM (GRP-IoM) and Uniformly Random Permutation-IoM (URP-IoM). As originally proposed, these schemes were claimed to be resistant against reversibility, authentication, and linkability attacks under the stolen token scenario. We propose several attacks against GRP-IoM and URP-IoM, and argue that both schemes are severely vulnerable against authentication and linkability attacks. We also propose better, but not yet practical, reversibility attacks against GRP-IoM. The correctness and practical impact of our attacks are verified over the same dataset provided by the authors of these two schemes. |
| Tasks | Cryptanalysis |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01389v3 |
| https://arxiv.org/pdf/1910.01389v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-cryptanalysis-of-two-cancelable-biometric |
| Repo | |
| Framework | |
Clustering and Classification Networks
| Title | Clustering and Classification Networks |
| Authors | Jin-mo Choi |
| Abstract | In this paper, we will describe a network architecture that demonstrates high performance on various sizes of datasets. To do this, we will perform an architecture search by dividing the fully connected layer into three levels in the existing network architecture. The first step is to learn existing CNN layer and existing fully connected layer for 1 epoch. The second step is clustering similar classes by applying L1 distance to the result of Softmax. The third step is to reclassify using clustering class masks. We accomplished the result of state-of-the-art by performing the above three steps sequentially or recursively. The technology recorded an error of 11.56% on Cifar-100. |
| Tasks | Neural Architecture Search |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08714v1 |
| https://arxiv.org/pdf/1906.08714v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-and-classification-networks |
| Repo | |
| Framework | |
Known-plaintext attack and ciphertext-only attack for encrypted single-pixel imaging
| Title | Known-plaintext attack and ciphertext-only attack for encrypted single-pixel imaging |
| Authors | Shuming Jiao, Yang Gao, Ting Lei, Zhenwei Xie, Xiaocong Yuan |
| Abstract | In many previous works, a single-pixel imaging (SPI) system is constructed as an optical image encryption system. Unauthorized users are not able to reconstruct the plaintext image from the ciphertext intensity sequence without knowing the illumination pattern key. However, little cryptanalysis about encrypted SPI has been investigated in the past. In this work, we propose a known-plaintext attack scheme and a ciphertext-only attack scheme to an encrypted SPI system for the first time. The known-plaintext attack is implemented by interchanging the roles of illumination patterns and object images in the SPI model. The ciphertext-only attack is implemented based on the statistical features of single-pixel intensity values. The two schemes can crack encrypted SPI systems and successfully recover the key containing correct illumination patterns. |
| Tasks | Cryptanalysis |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13594v1 |
| https://arxiv.org/pdf/1905.13594v1.pdf | |
| PWC | https://paperswithcode.com/paper/known-plaintext-attack-and-ciphertext-only |
| Repo | |
| Framework | |
Saliency-Guided Attention Network for Image-Sentence Matching
| Title | Saliency-Guided Attention Network for Image-Sentence Matching |
| Authors | Zhong Ji, Haoran Wang, Jungong Han, Yanwei Pang |
| Abstract | This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical architecture to represent both modalities, we propose Saliency-guided Attention Network (SAN) that asymmetrically employs visual and textual attention modules to learn the fine-grained correlation intertwined between vision and language. The proposed SAN mainly includes three components: saliency detector, Saliency-weighted Visual Attention (SVA) module, and Saliency-guided Textual Attention (STA) module. Concretely, the saliency detector provides the visual saliency information as the guidance for the two attention modules. SVA is designed to leverage the advantage of the saliency information to improve discrimination of visual representations. By fusing the visual information from SVA and textual information as a multi-modal guidance, STA learns discriminative textual representations that are highly sensitive to visual clues. Extensive experiments demonstrate SAN can substantially improve the state-of-the-art results on the benchmark Flickr30K and MSCOCO datasets by a large margin. |
| Tasks | |
| Published | 2019-04-20 |
| URL | https://arxiv.org/abs/1904.09471v3 |
| https://arxiv.org/pdf/1904.09471v3.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-guided-attention-network-for-image |
| Repo | |
| Framework | |
Hard Choices in Artificial Intelligence: Addressing Normative Uncertainty through Sociotechnical Commitments
| Title | Hard Choices in Artificial Intelligence: Addressing Normative Uncertainty through Sociotechnical Commitments |
| Authors | Roel Dobbe, Thomas Krendl Gilbert, Yonatan Mintz |
| Abstract | As AI systems become prevalent in high stakes domains such as surveillance and healthcare, researchers now examine how to design and implement them in a safe manner. However, the potential harms caused by systems to stakeholders in complex social contexts and how to address these remains unclear. In this paper, we explain the inherent normative uncertainty in debates about the safety of AI systems. We then address this as a problem of vagueness by examining its place in the design, training, and deployment stages of AI system development. We adopt Ruth Chang’s theory of intuitive comparability to illustrate the dilemmas that manifest at each stage. We then discuss how stakeholders can navigate these dilemmas by incorporating distinct forms of dissent into the development pipeline, drawing on Elizabeth Anderson’s work on the epistemic powers of democratic institutions. We outline a framework of sociotechnical commitments to formal, substantive and discursive challenges that address normative uncertainty across stakeholders, and propose the cultivation of related virtues by those responsible for development. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09005v1 |
| https://arxiv.org/pdf/1911.09005v1.pdf | |
| PWC | https://paperswithcode.com/paper/hard-choices-in-artificial-intelligence |
| Repo | |
| Framework | |
On Leveraging the Visual Modality for Neural Machine Translation
| Title | On Leveraging the Visual Modality for Neural Machine Translation |
| Authors | Vikas Raunak, Sang Keun Choe, Quanyang Lu, Yi Xu, Florian Metze |
| Abstract | Leveraging the visual modality effectively for Neural Machine Translation (NMT) remains an open problem in computational linguistics. Recently, Caglayan et al. posit that the observed gains are limited mainly due to the very simple, short, repetitive sentences of the Multi30k dataset (the only multimodal MT dataset available at the time), which renders the source text sufficient for context. In this work, we further investigate this hypothesis on a new large scale multimodal Machine Translation (MMT) dataset, How2, which has 1.57 times longer mean sentence length than Multi30k and no repetition. We propose and evaluate three novel fusion techniques, each of which is designed to ensure the utilization of visual context at different stages of the Sequence-to-Sequence transduction pipeline, even under full linguistic context. However, we still obtain only marginal gains under full linguistic context and posit that visual embeddings extracted from deep vision models (ResNet for Multi30k, ResNext for How2) do not lend themselves to increasing the discriminativeness between the vocabulary elements at token level prediction in NMT. We demonstrate this qualitatively by analyzing attention distribution and quantitatively through Principal Component Analysis, arriving at the conclusion that it is the quality of the visual embeddings rather than the length of sentences, which need to be improved in existing MMT datasets. |
| Tasks | Machine Translation, Multimodal Machine Translation |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02754v1 |
| https://arxiv.org/pdf/1910.02754v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-leveraging-the-visual-modality-for-neural |
| Repo | |
| Framework | |
Deep Discriminative Representation Learning with Attention Map for Scene Classification
| Title | Deep Discriminative Representation Learning with Attention Map for Scene Classification |
| Authors | Jun Li, Daoyu Lin, Yang Wang, Guangluan Xu, Chibiao Ding |
| Abstract | Learning powerful discriminative features for remote sensing image scene classification is a challenging computer vision problem. In the past, most classification approaches were based on handcrafted features. However, most recent approaches to remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is only to use original RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show class activation map (CAM) encoded CNN models, codenamed DDRL-AM, trained using original RGB patches and attention map based class information provide complementary information to the standard RGB deep models. To the best of our knowledge, we are the first to investigate attention information encoded CNNs. Additionally, to enhance the discriminability, we further employ a recently developed object function called “center loss,” which has proved to be very useful in face recognition. Finally, our framework provides attention guidance to the model in an end-to-end fashion. Extensive experiments on two benchmark datasets show that our approach matches or exceeds the performance of other methods. |
| Tasks | Face Recognition, Representation Learning, Scene Classification |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.07967v1 |
| http://arxiv.org/pdf/1902.07967v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-discriminative-representation-learning |
| Repo | |
| Framework | |
3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin
| Title | 3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin |
| Authors | Sergey Zakharov, Wadim Kehl, Benjamin Planche, Andreas Hutter, Slobodan Ilic |
| Abstract | In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks. Inspired by the descriptor learning approach of Wohlhart et al., we propose a method that introduces the dynamic margin in the manifold learning triplet loss function. Such a loss function is designed to map images of different objects under different poses to a lower-dimensional, similarity-preserving descriptor space on which efficient nearest neighbor search algorithms can be applied. Introducing the dynamic margin allows for faster training times and better accuracy of the resulting low-dimensional manifolds. Furthermore, we contribute the following: adding in-plane rotations (ignored by the baseline method) to the training, proposing new background noise types that help to better mimic realistic scenarios and improve accuracy with respect to clutter, adding surface normals as another powerful image modality representing an object surface leading to better performance than merely depth, and finally implementing an efficient online batch generation that allows for better variability during the training phase. We perform an exhaustive evaluation to demonstrate the effects of our contributions. Additionally, we assess the performance of the algorithm on the large BigBIRD dataset to demonstrate good scalability properties of the pipeline with respect to the number of models. |
| Tasks | Pose Estimation |
| Published | 2019-04-09 |
| URL | http://arxiv.org/abs/1904.04854v1 |
| http://arxiv.org/pdf/1904.04854v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-object-instance-recognition-and-pose |
| Repo | |
| Framework | |
Ranking Online Consumer Reviews
| Title | Ranking Online Consumer Reviews |
| Authors | Sunil Saumya, Jyoti Prakash Singh, Abdullah Mohammed Baabdullah, Nripendra P. Rana, Yogesh k. Dwivedi |
| Abstract | The product reviews are posted online in the hundreds and even in the thousands for some popular products. Handling such a large volume of continuously generated online content is a challenging task for buyers, sellers, and even researchers. The purpose of this study is to rank the overwhelming number of reviews using their predicted helpfulness score. The helpfulness score is predicted using features extracted from review text data, product description data and customer question-answer data of a product using random-forest classifier and gradient boosting regressor. The system is made to classify the reviews into low or high quality by random-forest classifier. The helpfulness score of the high-quality reviews is only predicted using gradient boosting regressor. The helpfulness score of the low-quality reviews is not calculated because they are never going to be in the top k reviews. They are just added at the end of the review list to the review-listing website. The proposed system provides fair review placement on review listing pages and making all high-quality reviews visible to customers on the top. The experimental results on data from two popular Indian e-commerce websites validate our claim, as 3-4 new high-quality reviews are placed in the top ten reviews along with 5-6 old reviews based on review helpfulness. Our findings indicate that inclusion of features from product description data and customer question-answer data improves the prediction accuracy of the helpfulness score. |
| Tasks | |
| Published | 2019-01-17 |
| URL | http://arxiv.org/abs/1901.06274v1 |
| http://arxiv.org/pdf/1901.06274v1.pdf | |
| PWC | https://paperswithcode.com/paper/ranking-online-consumer-reviews |
| Repo | |
| Framework | |
Highly Scalable and Flexible Model for Effective Aggregation of Context-based Data in Generic IIoT Scenarios
| Title | Highly Scalable and Flexible Model for Effective Aggregation of Context-based Data in Generic IIoT Scenarios |
| Authors | Simon Duque Anton, Daniel Fraunholz, Janis Zemitis, Frederic Pohl, Hans Dieter Schotten |
| Abstract | Interconnectivity of production machines is a key feature of the Industrial Internet of Things (IIoT). This feature allows for many advantages in producing. Configuration and maintenance gets easier, as access to the given production unit is not necessarily coupled to physical presence. Customized production of goods is easily possible, reducing production times and increasing throughput. There are, however, also dangers to the increasing talkativeness of industrial production machines. The more open a system is, the more points of entry for an attacker exist. Furthermore, the amount of data a production site also increases rapidly due to the integrated intelligence and interconnectivity. To keep track of this data in order to detect attacks and errors in the production site, it is necessary to smartly aggregate and evaluate the data. In this paper, we present a new approach for collecting, aggregating and analysing data from different sources and on three different levels of abstraction. Our model is event-centric, considering every occurrence of information inside the system as an event. In the lowest level of abstraction, singular packets are collected, correlated with log-entries and analysed. On the highest level of abstraction, networks are pictured as a connectivity graph, enriched with information about host-based activities. Furthermore, we describe our work in progress of evaluating our aggregation model on two different system settings. In the first scenario, we verify the usability of our model in a remote maintenance application. In the second scenario, we evaluate our model in the context of network sniffing and correlation with log-files. First results show that our model is a promising solution to cope with increasing amounts of data and to correlate information from different types of sources. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1906.03064v1 |
| https://arxiv.org/pdf/1906.03064v1.pdf | |
| PWC | https://paperswithcode.com/paper/highly-scalable-and-flexible-model-for |
| Repo | |
| Framework | |
Fair Classification and Social Welfare
| Title | Fair Classification and Social Welfare |
| Authors | Lily Hu, Yiling Chen |
| Abstract | Now that machine learning algorithms lie at the center of many resource allocation pipelines, computer scientists have been unwittingly cast as partial social planners. Given this state of affairs, important questions follow. What is the relationship between fairness as defined by computer scientists and notions of social welfare? In this paper, we present a welfare-based analysis of classification and fairness regimes. We translate a loss minimization program into a social welfare maximization problem with a set of implied welfare weights on individuals and groups–weights that can be analyzed from a distribution justice lens. In the converse direction, we ask what the space of possible labelings is for a given dataset and hypothesis class. We provide an algorithm that answers this question with respect to linear hyperplanes in $\mathbb{R}^d$ that runs in $O(n^dd)$. Our main findings on the relationship between fairness criteria and welfare center on sensitivity analyses of fairness-constrained empirical risk minimization programs. We characterize the ranges of $\Delta \epsilon$ perturbations to a fairness parameter $\epsilon$ that yield better, worse, and neutral outcomes in utility for individuals and by extension, groups. We show that applying more strict fairness criteria that are codified as parity constraints, can worsen welfare outcomes for both groups. More generally, always preferring “more fair” classifiers does not abide by the Pareto Principle—a fundamental axiom of social choice theory and welfare economics. Recent work in machine learning has rallied around these notions of fairness as critical to ensuring that algorithmic systems do not have disparate negative impact on disadvantaged social groups. By showing that these constraints often fail to translate into improved outcomes for these groups, we cast doubt on their effectiveness as a means to ensure justice. |
| Tasks | |
| Published | 2019-05-01 |
| URL | http://arxiv.org/abs/1905.00147v1 |
| http://arxiv.org/pdf/1905.00147v1.pdf | |
| PWC | https://paperswithcode.com/paper/fair-classification-and-social-welfare |
| Repo | |
| Framework | |
A BLSTM Network for Printed Bengali OCR System with High Accuracy
| Title | A BLSTM Network for Printed Bengali OCR System with High Accuracy |
| Authors | Debabrata Paul, Bidyut Baran Chaudhuri |
| Abstract | This paper presents a printed Bengali and English text OCR system developed by us using a single hidden BLSTM-CTC architecture having 128 units. Here, we did not use any peephole connection and dropout in the BLSTM, which helped us in getting better accuracy. This architecture was trained by 47,720 text lines that include English words also. When tested over 20 different Bengali fonts, it has produced character level accuracy of 99.32% and word level accuracy of 96.65%. A good Indic multi script OCR system is also developed by Google. It sometimes recognizes a character of Bengali into the same character of a non-Bengali script, especially Assamese, which has no distinction from Bengali, except for a few characters. For example, Bengali character for ‘RA’ is sometimes recognized as that of Assamese, mainly in conjunct consonant forms. Our OCR is free from such errors. This OCR system is available online at https://banglaocr.nltr.org |
| Tasks | Optical Character Recognition |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08674v1 |
| https://arxiv.org/pdf/1908.08674v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-blstm-network-for-printed-bengali-ocr |
| Repo | |
| Framework | |
When Specialization Helps: Using Pooled Contextualized Embeddings to Detect Chemical and Biomedical Entities in Spanish
| Title | When Specialization Helps: Using Pooled Contextualized Embeddings to Detect Chemical and Biomedical Entities in Spanish |
| Authors | Manuel Stoeckel, Wahed Hemati, Alexander Mehler |
| Abstract | The recognition of pharmacological substances, compounds and proteins is an essential preliminary work for the recognition of relations between chemicals and other biomedically relevant units. In this paper, we describe an approach to Task 1 of the PharmaCoNER Challenge, which involves the recognition of mentions of chemicals and drugs in Spanish medical texts. We train a state-of-the-art BiLSTM-CRF sequence tagger with stacked Pooled Contextualized Embeddings, word and sub-word embeddings using the open-source framework FLAIR. We present a new corpus composed of articles and papers from Spanish health science journals, termed the Spanish Health Corpus, and use it to train domain-specific embeddings which we incorporate in our model training. We achieve a result of 89.76% F1-score using pre-trained embeddings and are able to improve these results to 90.52% F1-score using specialized embeddings. |
| Tasks | Word Embeddings |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03387v1 |
| https://arxiv.org/pdf/1910.03387v1.pdf | |
| PWC | https://paperswithcode.com/paper/when-specialization-helps-using-pooled |
| Repo | |
| Framework | |
Escaping the State of Nature: A Hobbesian Approach to Cooperation in Multi-agent Reinforcement Learning
| Title | Escaping the State of Nature: A Hobbesian Approach to Cooperation in Multi-agent Reinforcement Learning |
| Authors | William Long |
| Abstract | Cooperation is a phenomenon that has been widely studied across many different disciplines. In the field of computer science, the modularity and robustness of multi-agent systems offer significant practical advantages over individual machines. At the same time, agents using standard reinforcement learning algorithms often fail to achieve long-term, cooperative strategies in unstable environments when there are short-term incentives to defect. Political philosophy, on the other hand, studies the evolution of cooperation in humans who face similar incentives to act individualistically, but nevertheless succeed in forming societies. Thomas Hobbes in Leviathan provides the classic analysis of the transition from a pre-social State of Nature, where consistent defection results in a constant state of war, to stable political community through the institution of an absolute Sovereign. This thesis argues that Hobbes’s natural and moral philosophy are strikingly applicable to artificially intelligent agents and aims to show that his political solutions are experimentally successful in producing cooperation among modified Q-Learning agents. Cooperative play is achieved in a novel Sequential Social Dilemma called the Civilization Game, which models the State of Nature by introducing the Hobbesian mechanisms of opponent learning awareness and majoritarian voting, leading to the establishment of a Sovereign. |
| Tasks | Multi-agent Reinforcement Learning, Q-Learning |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.09874v1 |
| https://arxiv.org/pdf/1906.09874v1.pdf | |
| PWC | https://paperswithcode.com/paper/escaping-the-state-of-nature-a-hobbesian |
| Repo | |
| Framework | |
